CS231n- 第二讲 图像分类

 1 # 将CIFAR-10的数据加载到内存中，并分成4个数组：训练数据和标签，测试数据和标签
  2 Xtr, Ytr, Xte, Yte = load_CIFAR10('data/cifar10/') # a magic function we provide
  3 # flatten out all images to be one-dimensional
  4 Xtr_rows = Xtr.reshape(Xtr.shape[0], 32 * 32 * 3) # Xtr_rows becomes 50000 x 3072
  5 Xte_rows = Xte.reshape(Xte.shape[0], 32 * 32 * 3) # Xte_rows becomes 10000 x 3072
  6
  7 nn = NearestNeighbor() # create a Nearest Neighbor classifier class
  8 nn.train(Xtr_rows, Ytr) # train the classifier on the training images and labels
  9 Yte_predict = nn.predict(Xte_rows) # predict labels on the test images
 10 # and now print the classification accuracy, which is the average number
 11 # of examples that are correctly predicted (i.e. label matches)
 12 print 'accuracy: %f' % ( np.mean(Yte_predict == Yte) )
 13
 14 import numpy as np
 15
 16 class NearestNeighbor(object):
 17   def __init__(self):
 18     pass
 19
 20   def train(self, X, y):
 21     """ X is N x D where each row is an example. Y is 1-dimension of size N """
 22     # the nearest neighbor classifier simply remembers all the training data
 23     self.Xtr = X
 24     self.ytr = y
 25
 26   def predict(self, X):
 27     """ X is N x D where each row is an example we wish to predict label for """
 28     num_test = X.shape[0]
 29     # lets make sure that the output type matches the input type
 30     Ypred = np.zeros(num_test, dtype = self.ytr.dtype)
 31
 32     # loop over all test rows
 33     for i in xrange(num_test):
 34       # find the nearest training image to the i'th test image
 35       # using the L1 distance (sum of absolute value differences)
 36       distances = np.sum(np.abs(self.Xtr - X[i,:]), axis = 1)
 37       min_index = np.argmin(distances) # get the index with smallest distance
 38       Ypred[i] = self.ytr[min_index] # predict the label of the nearest example
 39
 40     return Ypred

  1 # assume we have Xtr_rows, Ytr, Xte_rows, Yte as before
  2 # recall Xtr_rows is 50,000 x 3072 matrix
  3 Xval_rows = Xtr_rows[:1000, :] # take first 1000 for validation
  4 Yval = Ytr[:1000]
  5 Xtr_rows = Xtr_rows[1000:, :] # keep last 49,000 for train
  6 Ytr = Ytr[1000:]
  7
  8 # find hyperparameters that work best on the validation set
  9 validation_accuracies = []
 10 for k in [1, 3, 5, 10, 20, 50, 100]:
 11
 12   # use a particular value of k and evaluation on validation data
 13   nn = NearestNeighbor()
 14   nn.train(Xtr_rows, Ytr)
 15   # here we assume a modified NearestNeighbor class that can take a k as input
 16   Yval_predict = nn.predict(Xval_rows, k = k)
 17   acc = np.mean(Yval_predict == Yval)
 18   print 'accuracy: %f' % (acc,)
 19
 20   # keep track of what works on the validation set
 21   validation_accuracies.append((k, acc))